Claude
1567ea6de9
Critical fixes: - AnyAspectRatio: remove dead duplicate calculation that was overwriting itself with a wrong formula (correct formula kept on lines 55-56) - LoadImageResizer: fix trailing comma that made resized_mask a tuple instead of a value; properly convert alpha channel to float32 tensor - openAI_PoP: replace deprecated openai v0 API (openai.Image.create, openai.error.*) with modern openai>=1.0 client; fix hardcoded Windows backslash path with os.path.dirname(__file__); fix log/image dirs to be relative to module file instead of CWD - LoraStackLoaders: add missing `import comfy.sd` (was NameError at runtime); fix filter from l[0] (switch, never 'None') to l[1] (lora_name); fix `lora_name is None` to `== 'None'` for string comparison; fix display name mapping key LoraStackLoader10 -> LoraStackLoader10_PoP High severity fixes: - Conditioning: guard std() divisions with `if std > 0` to prevent NaN/Inf crash when tensor has zero variance - EfficientAttention: move dim_head calculation after dimension truncation so reshape is always valid; add divisibility check; fix output reshape to use min_dim not dim_q - VAEEncodeDecodeLoader: remove 5 debug print statements from decode() - CNutil: remove 3 debug print statements from resize_to_resolution() Minor fixes: - AdaptiveCannyDetector: fix `Category` -> `CATEGORY` (case-sensitive, ComfyUI was ignoring the node category) - LoadImageResizer: remove duplicate CATEGORY = "image" definition - requirements.txt: remove unused matplotlib/seaborn; add missing Pillow https://claude.ai/code/session_01QPLKoy7P41H3QPB6tMrpPh
92 lines
3.9 KiB
Python
92 lines
3.9 KiB
Python
class ConditioningMultiplier_PoP:
|
|
@classmethod
|
|
def INPUT_TYPES(cls):
|
|
return {"required": {"conditioning": ("CONDITIONING", ), "multiplier": ("FLOAT", {"default": 1.0, "min": -1, "max": 3.0})}}
|
|
|
|
RETURN_TYPES = ("CONDITIONING",)
|
|
FUNCTION = "multiply_conditioning_strength"
|
|
CATEGORY = "PoP"
|
|
|
|
def multiply_conditioning_strength(self, conditioning, multiplier):
|
|
# Validate the input types for 'conditioning' and 'multiplier'
|
|
if not isinstance(conditioning, list) or (not isinstance(multiplier, float) and not isinstance(multiplier, int)):
|
|
raise ValueError("Invalid input types")
|
|
|
|
#Initialize a new list to store the modified conditioning objects
|
|
new_conditioning = []
|
|
|
|
# Iterate through each element in the 'conditioning' list
|
|
for index, (tensor, attributes) in enumerate(conditioning):
|
|
# Multiply the tensor by the given multiplier
|
|
new_tensor = tensor.clone()
|
|
new_attributes = attributes.copy()
|
|
|
|
# Multiply the new tensor by the given multiplier
|
|
new_tensor *= multiplier
|
|
|
|
# If 'pooled_output' exists, scale it by the multiplier
|
|
if "pooled_output" in attributes:
|
|
new_pooled_output = attributes["pooled_output"].clone()
|
|
new_pooled_output *= multiplier
|
|
new_attributes["pooled_output"] = new_pooled_output
|
|
|
|
# Add the modified tensor and attributes to the new_conditioning list
|
|
new_conditioning.append([new_tensor, new_attributes])
|
|
|
|
|
|
# Return the modified 'conditioning' object
|
|
return (new_conditioning, ) # NOTE: Returning new_conditioning here
|
|
|
|
class ConditioningNormalizer_PoP:
|
|
@classmethod
|
|
def INPUT_TYPES(cls):
|
|
return {"required": {"conditioning": ("CONDITIONING", )}}
|
|
|
|
RETURN_TYPES = ("CONDITIONING",)
|
|
FUNCTION = "normalize_conditioning"
|
|
CATEGORY = "PoP"
|
|
|
|
def normalize_conditioning(self, conditioning):
|
|
# Validate the input type for 'conditioning'
|
|
if not isinstance(conditioning, list):
|
|
raise ValueError("Invalid input type")
|
|
|
|
# Initialize a new list to store the modified conditioning objects
|
|
new_conditioning = []
|
|
|
|
# Iterate through the 'conditioning' list
|
|
for index, (tensor, attributes) in enumerate(conditioning): #Q what is this doing? A iterating through the conditioning list
|
|
# Create new objects to store modified tensor and attributes
|
|
new_tensor = tensor.clone()
|
|
new_attributes = attributes.copy()
|
|
|
|
# Normalize the new tensor to have zero mean and unit variance
|
|
new_tensor -= new_tensor.mean()
|
|
std = new_tensor.std()
|
|
if std > 0:
|
|
new_tensor /= std
|
|
|
|
# If 'pooled_output' exists, normalize it
|
|
if "pooled_output" in attributes:
|
|
new_pooled_output = attributes["pooled_output"].clone()
|
|
new_pooled_output -= new_pooled_output.mean()
|
|
pooled_std = new_pooled_output.std()
|
|
if pooled_std > 0:
|
|
new_pooled_output /= pooled_std
|
|
new_attributes["pooled_output"] = new_pooled_output
|
|
|
|
# Add the modified tensor and attributes to the new_conditioning list
|
|
new_conditioning.append([new_tensor, new_attributes])
|
|
|
|
# Return the modified 'conditioning' object
|
|
return (new_conditioning, ) # NOTE: Returning new_conditioning here
|
|
|
|
#create node class mappings and node display name mappings
|
|
NODE_CLASS_MAPPINGS = {
|
|
"ConditioningMultiplier_PoP": ConditioningMultiplier_PoP,
|
|
"ConditioningNormalizer_PoP": ConditioningNormalizer_PoP
|
|
}
|
|
NODE_DISPLAY_NAME_MAPPINGS = {
|
|
"ConditioningMultiplier_PoP": "Conditioning Multiplier PoP",
|
|
"ConditioningNormalizer_PoP": "Conditioning Normalizer PoP"
|
|
} |